Extractive summarization in NLP - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

What is the main goal of extractive summarization?

Choose the best description of extractive summarization.

A Generating a summary by selecting important sentences directly from the original text.

B Creating new sentences that paraphrase the original text to form a summary.

C Translating the original text into another language before summarizing.

D Removing all stop words and punctuation to shorten the text.

💡 Hint

Think about whether the summary uses original sentences or new ones.

Extractive summarization picks key sentences from the original text without changing them, unlike abstractive summarization which generates new sentences.

❓ Predict Output

intermediate

Output of sentence scoring in extractive summarization

What is the output of this code that scores sentences by word frequency?

NLP

text = "Machine learning is fun. Learning machines can improve. Fun machines learn fast."
words = text.lower().replace('.', '').split()
freq = {}
for w in words:
    freq[w] = freq.get(w, 0) + 1
sentences = text.split('. ')
scores = {}
for s in sentences:
    score = 0
    for word in s.lower().split():
        score += freq.get(word, 0)
    scores[s] = score
print(scores)

A SyntaxError due to missing colon in for loop

B {'Machine learning is fun': 9, 'Learning machines can improve': 8, 'Fun machines learn fast.': 8}

C {'Machine learning is fun': 7, 'Learning machines can improve': 7, 'Fun machines learn fast.': 7}

D {'Machine learning is fun': 6, 'Learning machines can improve': 6, 'Fun machines learn fast.': 5}

💡 Hint

Count how many times each word appears and sum for each sentence.

The code counts word frequencies and sums them per sentence. Words like 'machine' and 'learning' appear multiple times, increasing scores.

❓ Model Choice

advanced

Best model type for extractive summarization on long documents

Which model is best suited for extractive summarization of very long documents?

A A convolutional neural network designed for image classification.

B A simple logistic regression model using bag-of-words features.

C A transformer model with a long input window like Longformer or BigBird.

D A recurrent neural network without attention mechanisms.

💡 Hint

Consider models that handle long text efficiently.

Longformer and BigBird are transformer models designed to process long texts efficiently, making them suitable for extractive summarization of long documents.

❓ Metrics

advanced

Which metric best evaluates extractive summarization quality?

Choose the metric that best measures how well an extractive summary matches a human summary.

A BLEU score used mainly for machine translation.

B ROUGE score, which compares overlapping n-grams between summaries.

C Accuracy of a classification model on sentiment labels.

D Mean Squared Error between summary word counts.

💡 Hint

Think about metrics that compare text overlap.

ROUGE measures overlap of words and phrases between generated and reference summaries, making it suitable for extractive summarization evaluation.

🔧 Debug

expert

Why does this extractive summarization code produce empty summary?

Given the code below, why does the summary list remain empty after execution?

NLP

text = "AI is transforming industries. It helps automate tasks."
sentences = text.split('. ')
summary = []
for s in sentences:
    if 'machine' in s.lower():
        summary.append(s)
print(summary)

A Because none of the sentences contain the word 'machine', so the condition is never true.

B Because the split method removes the last sentence, leaving summary empty.

C Because the summary list is overwritten inside the loop instead of appended.

D Because the print statement is outside the loop and summary is not defined globally.

💡 Hint

Check the condition inside the loop and the text content.

The code checks if 'machine' is in each sentence, but the text does not contain 'machine', so no sentences are added to summary.

Practice

1. What is the main goal of extractive summarization in NLP?

easy

A. To translate the text into another language

B. To rewrite the text using simpler words

C. To select important sentences from the original text to create a summary

D. To generate new sentences that explain the text

Solution

1. Step 1: Understand extractive summarization

   Extractive summarization picks key sentences directly from the original text without changing them.

2. Step 2: Compare options

   Only To select important sentences from the original text to create a summary describes selecting important sentences from the original text, which matches extractive summarization.

3. Final Answer:

   To select important sentences from the original text to create a summary -> Option C

4. Quick Check:

   Extractive summarization = selecting key sentences [OK]

Hint: Extractive means picking from original text directly [OK]

Common Mistakes:

• Confusing extractive with abstractive summarization
• Thinking it rewrites or translates text
• Assuming it generates new sentences

2. Which of the following is a common technique used in extractive summarization?

easy

A. Neural machine translation

B. Text generation with GPT

C. Part-of-speech tagging

D. TF-IDF scoring of sentences

Solution

1. Step 1: Identify techniques for extractive summarization

   Extractive summarization often uses TF-IDF to score sentences by importance based on word frequency.

2. Step 2: Eliminate unrelated options

   Neural machine translation and text generation are for other NLP tasks, and POS tagging is not directly used for summarization scoring.

3. Final Answer:

   TF-IDF scoring of sentences -> Option D

4. Quick Check:

   TF-IDF = common extractive technique [OK]

Hint: TF-IDF ranks sentence importance in extractive summarization [OK]

Common Mistakes:

• Confusing summarization with translation or generation
• Thinking POS tagging directly creates summaries
• Ignoring TF-IDF's role in scoring

3. Given the following Python code snippet using TF-IDF for extractive summarization, what will be the output?

from sklearn.feature_extraction.text import TfidfVectorizer

texts = ["Cats are great pets.", "Dogs are loyal animals.", "Cats and dogs can live together."]
vectorizer = TfidfVectorizer()
X = vectorizer.fit_transform(texts)
scores = X.sum(axis=1)
print(scores)

medium

A. [[0.0], [0.0], [0.0]]

B. [[2.0], [2.0], [2.4]]

C. [[2.0], [2.0], [3.0]]

D. [[1.0], [1.0], [1.0]]

Solution

1. Step 1: Understand TF-IDF vectorization and summing

   The code vectorizes three sentences and sums TF-IDF scores per sentence (row-wise sum).

2. Step 2: Calculate approximate sums

   Each sentence has TF-IDF scores summing roughly to 2.0, 2.0, and 2.4 respectively due to shared and unique words.

3. Final Answer:

   [[2.0], [2.0], [2.4]] -> Option B

4. Quick Check:

   Sum TF-IDF per sentence ≈ [[2.0], [2.0], [2.4]] [OK]

Hint: Sum TF-IDF scores per sentence to get importance [OK]

Common Mistakes:

• Assuming zero scores for all sentences
• Confusing sum with average
• Misunderstanding TF-IDF output shape

4. You have this extractive summarization code snippet:

sentences = ["AI is fascinating.", "It helps solve problems.", "AI can learn from data."]
scores = [0.8, 0.9, 0.85]
summary = []
for i in range(len(sentences)):
    if scores[i] > 0.85:
        summary.append(sentences[i])
print(summary)

What is the output and is there any bug?

medium

A. ['It helps solve problems.'] with no bug

B. ['AI is fascinating.', 'It helps solve problems.', 'AI can learn from data.'] with no bug

C. ['It helps solve problems.', 'AI can learn from data.'] but index error bug

D. [] because scores are not compared correctly

Solution

1. Step 1: Check score filtering condition

   The code adds sentences with scores > 0.85, so sentences with 0.9 and 0.85 are checked; 0.85 is not > 0.85, so only 0.9 and 0.85 fail or pass accordingly.

2. Step 2: Determine which sentences are included

   Scores: 0.8 (no), 0.9 (yes), 0.85 (no). So only "It helps solve problems." is included. But 0.85 is not > 0.85, so excluded.

3. Final Answer:

   ['It helps solve problems.'] -> Option A

4. Quick Check:

   Scores > 0.85 filter sentences correctly [OK]

Hint: Check strict > vs >= in score filtering [OK]

Common Mistakes:

• Including sentences with score equal to threshold
• Expecting index errors where none exist
• Misreading the comparison operator

5. You want to create an extractive summarizer that picks the top 2 sentences from a document based on TF-IDF scores. Given these sentences and their scores:

sentences = ["Machine learning is fun.", "It allows computers to learn.", "Summarization helps understand text.", "TF-IDF ranks sentence importance."]
scores = [0.7, 0.9, 0.6, 0.8]

Which two sentences should your summarizer select?

hard

A. ["It allows computers to learn.", "TF-IDF ranks sentence importance."]

B. ["Machine learning is fun.", "Summarization helps understand text."]

C. ["Summarization helps understand text.", "TF-IDF ranks sentence importance."]

D. ["Machine learning is fun.", "It allows computers to learn."]

Solution

1. Step 1: Identify top 2 scores

   The scores are 0.7, 0.9, 0.6, 0.8. The top two are 0.9 and 0.8.

2. Step 2: Match scores to sentences

   0.9 corresponds to "It allows computers to learn.", 0.8 corresponds to "TF-IDF ranks sentence importance.".

3. Final Answer:

   ["It allows computers to learn.", "TF-IDF ranks sentence importance."] -> Option A

4. Quick Check:

   Top 2 scores = 0.9 and 0.8 sentences [OK]

Hint: Pick sentences with highest TF-IDF scores [OK]

Common Mistakes:

• Choosing sentences with lower scores
• Mixing up sentence-score pairs
• Selecting more or fewer than top 2